© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10765
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" that indicate reasoning or conclusions are being drawn

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.67
    MCA
    -0.60
     }^{[
    -0.58
    choly
    -0.58
     McColl
    -0.54
    OOT
    -0.54
     बाद
    -0.54
     later
    -0.54
     transfieras
    -0.53
     Administrativna
    -0.53
    POSITIVE LOGITS
    horabuena
    0.70
     maș
    0.66
    
    0.64
    WithIOException
    0.61
    berdayakan
    0.60
    TintMode
    0.60
     saja
    0.59
     grosir
    0.57
    Hozzáférés
    0.57
     forth
    0.57
    Activations Density 0.093%

    No Known Activations